Questão 3

Imports

library(ggplot2)
library(dplyr)
library(plotly)

spotify_songs <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2020/2020-01-21/spotify_songs.csv')

genre_popularity <- spotify_songs %>% 
  select(c("playlist_genre", "track_popularity")) %>% 
  group_by(playlist_genre) %>% 
  summarise(track_popularity = mean(track_popularity)) %>%
  ungroup()

data <- genre_popularity %>% 
        rename(x = "playlist_genre", y = "track_popularity")

plot <- ggplot(data, aes(x=x, y=y)) +
  geom_segment( aes(x=x, xend=x, y=0, yend=y), color="grey") +
  geom_point( color="orange", size=4) +
  theme_light() +
  theme(
    panel.grid.major.x = element_blank(),
    panel.border = element_blank(),
    axis.ticks.x = element_blank()
  ) +
  xlab("Gênero") +
  ylab("Popularidade")

ggplotly(plot)

songs_attributes <- spotify_songs %>% 
  select(c("danceability", "energy", "tempo", "acousticness", "instrumentalness", "track_popularity", "playlist_genre")) %>% 
  group_by(playlist_genre) %>% 
  summarise(track_popularity = mean(track_popularity), danceability = mean(danceability), 
            energy = mean(energy), tempo = mean(tempo), acousticness = mean(acousticness), 
            instrumentalness = mean(instrumentalness)) %>% 
  ungroup()

numero_indice_b <- function(data){
  data_aux <- data
  data[1] <-  100; 
  
  for(i in 2:length(data)){
    data[i] <-  ( data_aux[i]/data_aux[i-1] ) * data[i-1]
  }
  
  return(data)
}

data_a <- songs_attributes %>%
  select(-playlist_genre) %>%
  purrr::map_df(function(x) x %>% numero_indice_b())

correl <-  cor(data_a) %>% round(2) 

corrplot::corrplot(correl, 
                   type = "upper",
                   tl.col = "black",
                   title = "Correlação entre atributos da música"
                   )